© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45572
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_22_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ਨੇ
    0.48
     الحياة
    0.47
     є
    0.47
    єр
    0.46
    є
    0.46
     गरे
    0.45
    OGND
    0.44
    І
    0.44
    cję
    0.44
     יכול
    0.42
    POSITIVE LOGITS
     caterpillars
    0.53
     extracts
    0.51
     staining
    0.51
     amphibians
    0.50
     penalties
    0.48
     extractive
    0.48
     antigens
    0.48
     brings
    0.47
     infestations
    0.47
     keratin
    0.46
    Activations Density 0.000%

    No Known Activations